Refine
Year of publication
- 2020 (2)
Document Type
- Article (2)
Language
- English (2)
Has Fulltext
- yes (2)
Is part of the Bibliography
- no (2)
Keywords
- Glioma (1)
- Isocitrate dehydrogenase (1)
- PWI (1)
- Pseudoprogression (1)
- [18F]FET PET (1)
- amino acid PET (1)
- artificial intelligence (1)
- glioma (1)
- treatment-related changes (1)
- tumor progression (1)
Institute
- Medizin (2)
Simple Summary: Pseudoprogression detection in glioblastoma patients remains a challenging task. Although pseudoprogression has only a moderate prevalence of 10–30% following first-line treatment of glioblastoma patients, it bears critical implications for affected patients. Non-invasive techniques, such as amino acid PET imaging using the tracer O-(2-[18F]-fluoroethyl)-L-tyrosine (FET), expose features that have been shown to provide useful information to distinguish tumor progression from pseudoprogression. The usefulness of FET-PET in IDH-wildtype glioblastoma exclusively, however, has not been investigated so far. Recently, machine learning (ML) algorithms have been shown to offer great potential particularly when multiparametric data is available. In this preliminary study, a Linear Discriminant Analysis-based ML algorithm was deployed in a cohort of newly diagnosed IDH-wildtype glioblastoma patients (n = 44) and demonstrated a significantly better diagnostic performance than conventional ROC analysis. This preliminary study is the first to assess the performance of ML in FET-PET for diagnosing pseudoprogression exclusively in IDH-wildtype glioblastoma and demonstrates its potential.
Abstract: Pseudoprogression (PSP) detection in glioblastoma remains challenging and has important clinical implications. We investigated the potential of machine learning (ML) in improving the performance of PET using O-(2-[18F]-fluoroethyl)-L-tyrosine (FET) for differentiation of tumor progression from PSP in IDH-wildtype glioblastoma. We retrospectively evaluated the PET data of patients with newly diagnosed IDH-wildtype glioblastoma following chemoradiation. Contrast-enhanced MRI suspected PSP/TP and all patients underwent subsequently an additional dynamic FET-PET scan. The modified Response Assessment in Neuro-Oncology (RANO) criteria served to diagnose PSP. We trained a Linear Discriminant Analysis (LDA)-based classifier using FET-PET derived features on a hold-out validation set. The results of the ML model were compared with a conventional FET-PET analysis using the receiver-operating-characteristic (ROC) curve. Of the 44 patients included in this preliminary study, 14 patients were diagnosed with PSP. The mean (TBRmean) and maximum tumor-to-brain ratios (TBRmax) were significantly higher in the TP group as compared to the PSP group (p = 0.014 and p = 0.033, respectively). The area under the ROC curve (AUC) for TBRmax and TBRmean was 0.68 and 0.74, respectively. Using the LDA-based algorithm, the AUC (0.93) was significantly higher than the AUC for TBRmax. This preliminary study shows that in IDH-wildtype glioblastoma, ML-based PSP detection leads to better diagnostic performance.
Purpose: Perfusion-weighted MRI (PWI) and O-(2-[18F]fluoroethyl-)-l-tyrosine ([18F]FET) PET are both applied to discriminate tumor progression (TP) from treatment-related changes (TRC) in patients with suspected recurrent glioma. While the combination of both methods has been reported to improve the diagnostic accuracy, the performance of a sequential implementation has not been further investigated. Therefore, we retrospectively analyzed the diagnostic value of consecutive PWI and [18F]FET PET.
Methods: We evaluated 104 patients with WHO grade II–IV glioma and suspected TP on conventional MRI using PWI and dynamic [18F]FET PET. Leakage corrected maximum relative cerebral blood volumes (rCBVmax) were obtained from dynamic susceptibility contrast PWI. Furthermore, we calculated static (i.e., maximum tumor to brain ratios; TBRmax) and dynamic [18F]FET PET parameters (i.e., Slope). Definitive diagnoses were based on histopathology (n = 42) or clinico-radiological follow-up (n = 62). The diagnostic performance of PWI and [18F]FET PET parameters to differentiate TP from TRC was evaluated by analyzing receiver operating characteristic and area under the curve (AUC).
Results: Across all patients, the differentiation of TP from TRC using rCBVmax or [18F]FET PET parameters was moderate (AUC = 0.69–0.75; p < 0.01). A rCBVmax cutoff > 2.85 had a positive predictive value for TP of 100%, enabling a correct TP diagnosis in 44 patients. In the remaining 60 patients, combined static and dynamic [18F]FET PET parameters (TBRmax, Slope) correctly discriminated TP and TRC in a significant 78% of patients, increasing the overall accuracy to 87%. A subgroup analysis of isocitrate dehydrogenase (IDH) mutant tumors indicated a superior performance of PWI to [18F]FET PET (AUC = 0.8/< 0.62, p < 0.01/≥ 0.3).
Conclusion: While marked hyperperfusion on PWI indicated TP, [18F]FET PET proved beneficial to discriminate TP from TRC when PWI remained inconclusive. Thus, our results highlight the clinical value of sequential use of PWI and [18F]FET PET, allowing an economical use of diagnostic methods. The impact of an IDH mutation needs further investigation.